Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to content below

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mhm
    0.54
     Aufbau
    0.50
     auparavant
    0.50
     alcanz
    0.49
     Souza
    0.49
     unui
    0.48
     nagu
    0.47
     ryzy
    0.47
     aaye
    0.47
     proporcion
    0.46
    POSITIVE LOGITS
    👇
    0.55
    。
    0.48
     below
    0.46
    .
    0.46
    ↓
    0.45
     👇
    0.45
    гре
    0.44
    ↓↓
    0.42
    țial
    0.41
    યા
    0.41
    Act Density 0.091%

    No Known Activations